generic-library/vpx
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
17,281 Commits 55 Branches 16 Tags 63 MiB
6444958f62
Commit Graph

17281 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Linfeng Zhang
d5de63d2be Update highbd idct functions arguments to use uint16_t dst 
BUG=webm:1388

Change-Id: I3581d80d0389b99166e70987d38aba2db6c469d5
 2017-05-03 13:59:16 -07:00
Linfeng Zhang
081b39f2b7 Clean CONVERT_TO_BYTEPTR/SHORTPTR in idct 
BUG=webm:1388

Change-Id: Ida62c941f2b836d6c9e27b427a7d5008ab6dc112
 2017-05-03 13:58:31 -07:00
Hui Su
5048d6e7ee Merge "vp9 level: add tentative max cpb values for high levels" 2017-05-03 20:51:03 +00:00
Hui Su
f701a44305 Merge "Adjust alt-ref selection in define_gf_group()" 2017-05-03 20:50:29 +00:00
Yi Luo
a3452996a1 High bit depth inter prediction horizontal/vertical filters AVX2 
User level speed improvement on i7-6700, cpu-used=1,
  x86_64 Linux, bitrate, 1080p, 8Mbps, 4K, 16Mbps:
- Decoder:
  1080p: ~4%
  4K: ~5%
- Encoder:
  1080p: ~1%
  4K: ~3%

Change-Id: I51b48f9c5de0d62487d5a11aa579c97bd03dd640
 2017-05-03 12:18:01 -07:00
Linfeng Zhang
a10a5cb356 Merge changes I8bb660de,Ica51d780,I6037525d 
* changes:
  Clean specializes of idct functions
  Clean add_protos of highbd idct functions
  Clean add_protos of idct functions
 2017-05-03 19:17:55 +00:00
James Zern
5599e4275a Merge changes Ia5293d94,I90d481d3,Ia509d622,I54549b03,I89b635d6 
* changes:
  ppc: Add convolve8_vsx and convolve8_avg_vsx
  ppc: Add convolve8_avg_vert_vsx
  ppc: Add convolve8_vert
  ppc: Add convolve8_horiz_avg
  ppc: Add convolve8_horiz
 2017-05-03 03:31:19 +00:00
Luca Barbato
e2ad89092d ppc: Add convolve8_vsx and convolve8_avg_vsx 
Change-Id: Ia5293d948003a7fff5a7cbad6e83d8a72717c857
 2017-05-02 20:27:47 -07:00
Luca Barbato
e6ca81ee67 ppc: Add convolve8_avg_vert_vsx 
Only the generic one again, speedups for 8x8 and larger blocks to
come later.

Change-Id: I90d481d3a602d1e277ead8f3934eca126b86b72d
 2017-05-02 20:27:42 -07:00
Luca Barbato
a65f1771ad ppc: Add convolve8_vert 
Only the generic one again, speedups for 8x8 and larger blocks
to come later.

Change-Id: Ia509d6225984b4930ec03928c9bcbf51486da99f
 2017-05-02 20:27:33 -07:00
Luca Barbato
77772350f3 ppc: Add convolve8_horiz_avg 
The 8x8 and larger blocks cases can be sped up further.

Change-Id: I54549b03ac6c7a4e3f485738b100c3cac7ac2e15
 2017-05-02 20:27:28 -07:00
Luca Barbato
08edb85bd0 ppc: Add convolve8_horiz 
The 8x8 and larger blocks cases can be sped up further.

Change-Id: I89b635d6b01c59f523f2d54b1284ed32916c5046
 2017-05-02 20:27:16 -07:00
Linfeng Zhang
0178d974e5 Clean specializes of idct functions 
Change-Id: I8bb660de47b5f97263ec381dc428db96e9c9a4b2
 2017-05-02 18:01:19 -07:00
Linfeng Zhang
4412996d59 Clean add_protos of highbd idct functions 
Change-Id: Ica51d780b92b316ce9112740c56cdf7670816371
 2017-05-02 17:59:38 -07:00
Linfeng Zhang
a7a57d9756 Clean add_protos of idct functions 
Change-Id: I6037525d92ec172810edab720389eb1865ed3b1a
 2017-05-02 17:58:40 -07:00
Johann Koenig
240a5a15ef Merge "block error sse2: sum in 32 bits when possible" 2017-05-02 14:16:47 +00:00
Johann
cd94d5f68e block error avx2: rename variables 
Change-Id: I2b8a9253f2c3d1fd85304c2970ebe70213870fe9
 2017-05-01 17:54:29 -07:00
Johann Koenig
b1a31f8066 Merge "block error avx2: sum in 32 bits when possible" 2017-05-02 00:52:59 +00:00
Marco Paniconi
1e112bce37 Merge "vp9: SVC: Early exit on golden ref in non-rd pickmode." 2017-05-01 21:04:52 +00:00
Linfeng Zhang
e8655d49f5 Merge "Clean vp9_highbd_build_inter_predictor() and highbd_inter_predictor()" 2017-05-01 19:54:40 +00:00
Johann Koenig
3d33a462b3 Merge "move vp9_error_intrin_avx2.c" 2017-05-01 19:52:36 +00:00
Kyle Siefring
760c214519 block error avx2: sum in 32 bits when possible 
Add 31bit pairs before unpacking in x86 block error code

AVX2 code provides a very minor performance improvement.

BUG=webm:1210

Change-Id: I4c82308eaf65741dca2f5c6db9be9c85f905073a
 2017-05-01 12:51:33 -07:00
James Zern
ee3df31d74 Merge "vpx_scale_test: fix segfault on alloc failure" 2017-05-01 19:22:22 +00:00
Marco
ae0215f945 vp9: SVC: Early exit on golden ref in non-rd pickmode. 
For SVC 1 pass real-time: add condition to skip the
golden (spatial) reference mode in non-rd pickmode.
Condition is to skip golden if the sse of zeromv-last mode
is below threshold. And change order in ref_mode_set_svc
to make sure golden zeromv is tested after last-nearest.

Speedup ~3-4% with little/negligible quality loss.

Change-Id: I6cbe314a93210454ba2997945f714015f1b2fca3
 2017-05-01 10:36:54 -07:00
Kyle Siefring
8394990b27 block error sse2: sum in 32 bits when possible 
Add 31bit pairs before unpacking in x86 block error code

BUG=webm:1210

Change-Id: I5ca8c7f7775585a17fe09d6bbfc25e1f2955eb0a
 2017-05-01 09:59:18 -07:00
Johann
2ff01aa1e4 move vp9_error_intrin_avx2.c 
There is only one avx2 implementation. Drop '_intrin'

Change-Id: I887a0d27d58567eaad49f749f127eca61313f312
 2017-05-01 09:13:01 -07:00
James Zern
2930903d51 vpx_scale_test: fix segfault on alloc failure 
check the return of ResetImage() before continuing

Change-Id: Iff0b038f7b9761113b8cf33a511a5306640d1273
 2017-04-29 13:12:53 -07:00
Luca Barbato
d51d3934f5 ppc: Add convolve_avg 
Change-Id: Ib203c444c708f42072e38301ee3db97b5b53d014
 2017-04-29 15:47:25 +02:00
Luca Barbato
63860ba7b8 ppc: Add convolve_copy 
Change-Id: Ie26d6dbe090e711d84bac01ba7da270db983f405
 2017-04-29 15:47:25 +02:00
Johann Koenig
ef5918098d Merge "Use uint32_t for accumulator" 2017-04-28 18:32:09 +00:00
Jerome Jiang
ce2e278059 Merge "vp9: Fix condition for disabling adaptive_rd_thresh." 2017-04-28 18:10:36 +00:00
Jerome Jiang
04de501229 vp9: Fix condition for disabling adaptive_rd_thresh. 
Add speed constrains for disabling adaptive_rd_thresh when
row_mt_bit_exact is set.

Change-Id: I2445115c2f9a2e46b8a0966031a0fea488d4964e
 2017-04-28 10:26:20 -07:00
Jerome Jiang
bea27a5809 Merge "Generalize vp9 sse2 denoiser test for other platforms." 2017-04-28 15:45:52 +00:00
Johann
657f3e9f14 Use uint32_t for accumulator 
Be specific about the data type size.

Use convenience macro vp9_zero_array.

Change-Id: I5fadf7dbd408befb73820d85db0be4832e8cfcbd
 2017-04-28 06:36:59 -07:00
Johann Koenig
94ebdba71d Merge "vp9 temporal filter: sse4 implementation" 2017-04-28 13:22:41 +00:00
Jerome Jiang
26aebd77b8 Generalize vp9 sse2 denoiser test for other platforms. 
Renamed to vp9_denoiser_test.

Change-Id: I0d8f4c94bcb81a60949a13d9fe839cee95d03f77
 2017-04-27 22:47:41 -07:00
Yaowu Xu
0e8fea6c13 Merge "VP9: enable trellis for high bitdepth intra" 2017-04-28 00:16:56 +00:00
James Zern
ef15d38df0 Merge "webm_read_frame: avoid NULL dereference" 2017-04-27 21:47:10 +00:00
Johann
6dfeea6592 vp9 temporal filter: sse4 implementation 
Approximates division using multiply and shift.

Speeds up both sizes (8x8 and 16x16) by 30 times.

Fix the call sites to use the RTCD function.

Delete sse2 and mips implementation. They were based on a previous
implementation of the filter. It was changed in Dec 2015:
ece4fd5d22

BUG=webm:1378

Change-Id: I0818e767a802966520b5c6e7999584ad13159276
 2017-04-26 22:03:05 -07:00
Jerome Jiang
43e0e082d1 vp9: Don't force disabling of adaptive_rd_thresh for realtime. 
Don't force disabling of adaptive_rd_thresh for realtime when
row_mt_bit_exact is set.

Row based adaptive rd is made usable in CL
454882(https://chromium-review.googlesource.com/c/454882) for REALTIME.

Change-Id: Ief023414f0fd6eb86f299dd46ae58f4436875af5
 2017-04-26 13:17:57 -07:00
Yunqing Wang
b68f14d0ed Merge "Make the row based multi-threaded encoder deterministic" 2017-04-26 16:12:14 +00:00
Linfeng Zhang
54c4e0f7a5 Merge "Update highbd convolve functions arguments to use uint16_t src/dst" 2017-04-26 15:50:46 +00:00
Marco Paniconi
004fab120a Merge "vp9: SVC: Adjust some speed settings for temporal layers." 2017-04-26 15:45:06 +00:00
Peter de Rivaz
66117b97c5 VP9: enable trellis for high bitdepth intra 
BUG=webm:1409

Change-Id: I5236595aac1c09386c60ffe8ad621e01422ed5a7
 2017-04-26 11:43:01 +01:00
hui su
d01c9febe9 vp9 level: add tentative max cpb values for high levels 
Add tentative max cpb size values for levels 5.2 and up. Otherwise
encoding will fail when targeting for these levels.

Change-Id: Ib7e0ba4b9836ea1ac900b6822543812843d48463
 2017-04-25 18:03:55 -07:00
hui su
8069f31076 Adjust alt-ref selection in define_gf_group() 
107de19698 changes the encoder alt-ref selection behavior. Assuming
min_gf_interval = max_gf_interval = 4, the frame order would be
frm_1  arf_1  frm_2  frm_3  frm_4  frm_5  arf_2 before 107de19698;
frm_1  arf_1  frm_2  frm_3  frm_4  arf_2  frm_5 after 107de19698.

This patch reverts such alt-ref placement change.

Change-Id: I93a4a65036575151286f004d455d4fcea88a1550
 2017-04-25 18:03:47 -07:00
Jerome Jiang
15ee8a8c45 Merge "Fix the decoder seg fault when frame is corrupted." 2017-04-26 00:09:29 +00:00
Jerome Jiang
997e54ea43 Merge "vp9: speed >= 8: Skip uv variance in model_rd_sb_y_large" 2017-04-26 00:09:22 +00:00
Marco
c614164cb6 vp9: SVC: Adjust some speed settings for temporal layers. 
Make some speed setting changes for temporal enhancement layers,
and remove the switch in subpel_force_stop for the aggressive_base_mv
in non-rd pickmode.

Gain some 2-3% speed with little/negligible quality loss.

Change-Id: I3e2a7f80ff45f38c0a6ceb01b34dbca2f53edbf0
 2017-04-25 16:27:01 -07:00
Jerome Jiang
69b0242e9a vp9: speed >= 8: Skip uv variance in model_rd_sb_y_large 
For speed >= 8 and color_sensitivity not set, skip the transform
skipping test in UV planes.
Add a new condition to check noise level to skip chroma check
for speed >= 8 if y_sad is high.

1~2% speedup on ARM for speed 8.

Borg tests show neutral results in both rtc and rtc_derf.

Change-Id: Idecd3ff6e28c97757a43bb6f3a7082c85f72109c
 2017-04-25 16:21:36 -07:00